QuestBench - Mean Score: leaderboard
QuestBench (2026) holds 256 expert-level deep research questions in Chinese from 14 humanities and social-science domains, designed and adversarially reviewed by students and answered with web search and visit tools. This board is the mean graded score from 0 to 100; higher is better.
Metric: Mean score (0-100) against question-specific grading criteria over the 256 Chinese deep research questions, with identical web search and visit tools and a nominal 50-call budget per question; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 13 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.5 | 67.12 | #54 |
| 2 | Claude Opus 4.7 | 57.79 | #85 |
| 3 | Gemini 3.1 Pro (Preview) | 43.07 | #99 |
| 4 | GLM-5.1 | 42.3 | #198 |
| 5 | DeepSeek V4 Pro | 38.24 | #196 |
| 6 | Kimi K2.6 | 37.74 | #192 |
| 7 | Qwen 3.6 Plus | 36.05 | #238 |
| 8 | MiMo-V2.5-Pro | 32.05 | #284 |
| 9 | Kimi K2.5 | 30.48 | #266 |
| 10 | MiniMax-M2.7 | 29.29 | #539 |
| 11 | Seed-2 Pro | 22.89 | |
| 12 | Seed-1.8 Pro | 22.07 | |
| 13 | DeepSeek V3.2 | 14.58 | #419 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=questbench-mean-score · How It Works · Data refreshed daily, snapshot 2026-11-21.